agentic-qe 3.8.1 → 3.8.3

package/assets/skills/trust-tier-manifest.json

@@ -5,17 +5,17 @@
   "generator": "scripts/update-skill-manifest.ts",
   "trustTierPolicy": "ADR-056",
   "summary": {
-    "tier0": 41,
+    "tier0": 51,
     "tier1": 5,
     "tier2": 7,
-    "tier3": 51,
-    "total": 104
+    "tier3": 49,
+    "total": 112
   },
   "validationStatus": {
-    "passing": 51,
+    "passing": 49,
     "failing": 0,
     "unknown": 12,
-    "skipped": 41
+    "skipped": 51
   },
   "skillsByTier": {
     "tier3": [
@@ -314,16 +314,6 @@
         },
         "file": "qe-code-intelligence/SKILL.md"
       },
-      {
-        "name": "qe-contract-testing",
-        "validation": {
-          "status": "passing",
-          "schemaPath": "schemas/output.json",
-          "validatorPath": "scripts/validate-config.json",
-          "evalPath": "evals/qe-contract-testing.yaml"
-        },
-        "file": "qe-contract-testing/SKILL.md"
-      },
       {
         "name": "qe-coverage-analysis",
         "validation": {
@@ -374,16 +364,6 @@
         },
         "file": "qe-requirements-validation/SKILL.md"
       },
-      {
-        "name": "qe-security-compliance",
-        "validation": {
-          "status": "passing",
-          "schemaPath": "schemas/output.json",
-          "validatorPath": "scripts/validate-config.json",
-          "evalPath": "evals/qe-security-compliance.yaml"
-        },
-        "file": "qe-security-compliance/SKILL.md"
-      },
       {
         "name": "qe-test-execution",
         "validation": {
@@ -650,14 +630,6 @@
         },
         "file": "agentic-quality-engineering/SKILL.md"
       },
-      {
-        "name": "aqe-v2-v3-migration",
-        "validation": {
-          "status": "unknown",
-          "schemaPath": "schemas/output.json"
-        },
-        "file": "aqe-v2-v3-migration/SKILL.md"
-      },
       {
         "name": "consultancy-practices",
         "category": "professional-practice",
@@ -716,6 +688,16 @@
         "category": "testing-methodologies",
         "file": "context-driven-testing/SKILL.md"
       },
+      {
+        "name": "coverage-drop-investigator",
+        "category": "investigation",
+        "file": "coverage-drop-investigator/SKILL.md"
+      },
+      {
+        "name": "coverage-guard",
+        "category": "on-demand-hooks",
+        "file": "coverage-guard/SKILL.md"
+      },
       {
         "name": "debug-loop",
         "category": "debugging",
@@ -724,6 +706,11 @@
         },
         "file": "debug-loop/SKILL.md"
       },
+      {
+        "name": "e2e-flow-verifier",
+        "category": "product-verification",
+        "file": "e2e-flow-verifier/SKILL.md"
+      },
       {
         "name": "exploratory-testing-advanced",
         "category": "testing-methodologies",
@@ -744,6 +731,11 @@
         "category": "orchestration",
         "file": "flow-nexus-swarm/SKILL.md"
       },
+      {
+        "name": "freeze-tests",
+        "category": "on-demand-hooks",
+        "file": "freeze-tests/SKILL.md"
+      },
       {
         "name": "github-code-review",
         "category": "github",
@@ -787,6 +779,11 @@
         "name": "iterative-loop",
         "file": "iterative-loop/SKILL.md"
       },
+      {
+        "name": "no-skip",
+        "category": "on-demand-hooks",
+        "file": "no-skip/SKILL.md"
+      },
       {
         "name": "pair-programming",
         "file": "pair-programming/SKILL.md"
@@ -807,6 +804,11 @@
         "name": "reasoningbank-intelligence",
         "file": "reasoningbank-intelligence/SKILL.md"
       },
+      {
+        "name": "security-watch",
+        "category": "on-demand-hooks",
+        "file": "security-watch/SKILL.md"
+      },
       {
         "name": "six-thinking-hats",
         "category": "methodology",
@@ -816,11 +818,21 @@
         "name": "skill-builder",
         "file": "skill-builder/SKILL.md"
       },
+      {
+        "name": "skill-stats",
+        "category": "measurement",
+        "file": "skill-stats/SKILL.md"
+      },
       {
         "name": "sparc-methodology",
         "category": "development",
         "file": "sparc-methodology/SKILL.md"
       },
+      {
+        "name": "strict-tdd",
+        "category": "on-demand-hooks",
+        "file": "strict-tdd/SKILL.md"
+      },
       {
         "name": "stream-chain",
         "category": "workflow",
@@ -835,6 +847,16 @@
         "name": "swarm-orchestration",
         "file": "swarm-orchestration/SKILL.md"
       },
+      {
+        "name": "test-failure-investigator",
+        "category": "investigation",
+        "file": "test-failure-investigator/SKILL.md"
+      },
+      {
+        "name": "test-metrics-dashboard",
+        "category": "analytics",
+        "file": "test-metrics-dashboard/SKILL.md"
+      },
       {
         "name": "v3-cli-modernization",
         "file": "v3-cli-modernization/SKILL.md"
@@ -1361,16 +1383,6 @@
       },
       "file": "qe-code-intelligence/SKILL.md"
     },
-    "qe-contract-testing": {
-      "trustTier": 3,
-      "validation": {
-        "status": "passing",
-        "schemaPath": "schemas/output.json",
-        "validatorPath": "scripts/validate-config.json",
-        "evalPath": "evals/qe-contract-testing.yaml"
-      },
-      "file": "qe-contract-testing/SKILL.md"
-    },
     "qe-coverage-analysis": {
       "trustTier": 3,
       "validation": {
@@ -1421,16 +1433,6 @@
       },
       "file": "qe-requirements-validation/SKILL.md"
     },
-    "qe-security-compliance": {
-      "trustTier": 3,
-      "validation": {
-        "status": "passing",
-        "schemaPath": "schemas/output.json",
-        "validatorPath": "scripts/validate-config.json",
-        "evalPath": "evals/qe-security-compliance.yaml"
-      },
-      "file": "qe-security-compliance/SKILL.md"
-    },
     "qe-test-execution": {
       "trustTier": 3,
       "validation": {
@@ -1923,14 +1925,6 @@
       ],
       "lastUpdated": "2025-12-02"
     },
-    "aqe-v2-v3-migration": {
-      "trustTier": 1,
-      "validation": {
-        "status": "unknown",
-        "schemaPath": "schemas/output.json"
-      },
-      "file": "aqe-v2-v3-migration/SKILL.md"
-    },
     "consultancy-practices": {
       "trustTier": 1,
       "category": "professional-practice",
@@ -2050,6 +2044,30 @@
       ],
       "lastUpdated": "2025-12-02"
     },
+    "coverage-drop-investigator": {
+      "trustTier": 0,
+      "category": "investigation",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "coverage-drop-investigator/SKILL.md"
+    },
+    "coverage-guard": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "coverage-guard/SKILL.md"
+    },
+    "e2e-flow-verifier": {
+      "trustTier": 0,
+      "category": "product-verification",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "e2e-flow-verifier/SKILL.md"
+    },
     "exploratory-testing-advanced": {
       "trustTier": 0,
       "category": "testing-methodologies",
@@ -2109,6 +2127,14 @@
         "message-queue"
       ]
     },
+    "freeze-tests": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "freeze-tests/SKILL.md"
+    },
     "github-code-review": {
       "trustTier": 0,
       "category": "github",
@@ -2225,6 +2251,14 @@
       },
       "file": "iterative-loop/SKILL.md"
     },
+    "no-skip": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "no-skip/SKILL.md"
+    },
     "pair-programming": {
       "trustTier": 0,
       "validation": {
@@ -2246,6 +2280,14 @@
       },
       "file": "reasoningbank-intelligence/SKILL.md"
     },
+    "security-watch": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "security-watch/SKILL.md"
+    },
     "six-thinking-hats": {
       "trustTier": 0,
       "category": "methodology",
@@ -2271,6 +2313,14 @@
       },
       "file": "skill-builder/SKILL.md"
     },
+    "skill-stats": {
+      "trustTier": 0,
+      "category": "measurement",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "skill-stats/SKILL.md"
+    },
     "sparc-methodology": {
       "trustTier": 0,
       "category": "development",
@@ -2279,6 +2329,14 @@
       },
       "file": "sparc-methodology/SKILL.md"
     },
+    "strict-tdd": {
+      "trustTier": 0,
+      "category": "on-demand-hooks",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "strict-tdd/SKILL.md"
+    },
     "stream-chain": {
       "trustTier": 0,
       "category": "workflow",
@@ -2318,6 +2376,22 @@
       },
       "file": "swarm-orchestration/SKILL.md"
     },
+    "test-failure-investigator": {
+      "trustTier": 0,
+      "category": "investigation",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "test-failure-investigator/SKILL.md"
+    },
+    "test-metrics-dashboard": {
+      "trustTier": 0,
+      "category": "analytics",
+      "validation": {
+        "status": "skipped"
+      },
+      "file": "test-metrics-dashboard/SKILL.md"
+    },
     "v3-cli-modernization": {
       "trustTier": 0,
       "validation": {

package/assets/skills/validation-pipeline/SKILL.md

@@ -1,19 +1,18 @@
 ---
 name: "Validation Pipeline"
-description: "Structured step-by-step validation of requirements, code, and artifacts with gate enforcement, per-step scoring, and structured reports."
+description: "Use when validating requirements, code, or artifacts through structured gate enforcement with per-step scoring and pass/fail reports."
 trust_tier: 3
 validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/validation-pipeline.yaml
-
 ---
 
 # Validation Pipeline
 
 ## Purpose
 
-Run structured validation pipelines that execute steps sequentially, enforce gates at blocking failures, and produce scored reports. Uses the `src/validation/pipeline.ts` framework with 13 requirements validation steps (BMAD-003).
+Run structured validation pipelines that execute steps sequentially, enforce gates at blocking failures, and produce scored reports. Uses `.claude/helpers/validation-pipeline.cjs` with 13 requirements validation steps (BMAD-003).
 
 ## Activation
 
@@ -57,11 +56,11 @@ Choose the appropriate pipeline based on the user's request:
 |----------|-------|----------|
 | `requirements` | 13 | Requirements documents, PRDs, user stories |
 
-Additional pipelines can be created by defining new step sets in `src/validation/steps/`.
+Additional pipelines can be added to `.claude/helpers/validation-pipeline.cjs`.
 
 ### Step 3: Execute Pipeline
 
-The pipeline framework (`src/validation/pipeline.ts`) handles execution:
+The pipeline helper (`.claude/helpers/validation-pipeline.cjs`) handles execution:
 
 1. **Sequential execution** — steps run in order, each receiving results from prior steps
 2. **Gate enforcement** — blocking steps that fail halt the pipeline (unless `--continue-on-failure`)
@@ -126,7 +125,7 @@ memory store --namespace validation-pipeline --key "req-validation-{timestamp}"
 |-----------|------|---------|-------------|
 | `pipeline` | string | `requirements` | Pipeline type to run |
 | `file` | string | required | Path to document to validate |
-| `--steps` | string[] | all | Specific step IDs to run |
+| `--steps` | string | all | Comma-separated step IDs to run (e.g., `format-check,completeness-check`) |
 | `--continue-on-failure` | boolean | false | Skip blocking gates |
 | `--json` | boolean | false | Output as JSON instead of markdown |
 | `--metadata` | object | {} | Additional context for steps |

package/assets/skills/verification-quality/SKILL.md

@@ -1,6 +1,6 @@
 ---
 name: "Verification & Quality Assurance"
-description: "Comprehensive truth scoring, code quality verification, and automatic rollback system with 0.95 accuracy threshold for ensuring high-quality agent outputs and codebase reliability."
+description: "Use when verifying agent outputs are correct, validating code changes before merge, or setting up automatic rollback for failed quality checks."
 version: "2.0.0"
 category: "quality-assurance"
 tags: ["verification", "truth-scoring", "quality", "rollback", "metrics", "ci-cd"]
@@ -641,6 +641,20 @@ Verification commands return standard exit codes:
 7. **Review Rollbacks**: Understand why changes were rejected
 8. **Train Agents**: Use verification feedback to improve agent performance
 
+## Skill Composition
+
+- **Before verification** → Run `/qe-test-generation` and `/qe-coverage-analysis` first
+- **If verification fails** → Use `/test-failure-investigator` for root cause analysis
+- **Ship decision** → Feed into `/qe-quality-assessment` for final assessment
+
+## Gotchas
+
+- Verification is the HIGHEST-VALUE skill category (Anthropic: "worth having an engineer spend a week making verification skills excellent")
+- "Success is silent, only failures are verbose" — swallow passing test output, surface only errors to avoid context window flooding
+- Agent completion claims are unreliable — always include programmatic assertions on state, not just "looks right"
+- Have Claude record a video of its output so you can see exactly what it tested (Playwright trace, screenshot evidence)
+- Hardcoded values are the #1 completion theater pattern — grep for literals that should be dynamic
+
 ### Additional Resources
 
 - Truth Scoring Algorithm: See `/docs/truth-scoring.md`

package/assets/skills/visual-testing-advanced/SKILL.md

@@ -16,7 +16,6 @@ validation:
   schema_path: schemas/output.json
   validator_path: scripts/validate-config.json
   eval_path: evals/visual-testing-advanced.yaml
-
 ---
 
 # Advanced Visual Testing

package/assets/skills/xp-practices/SKILL.md

@@ -13,7 +13,6 @@ quick_reference_card: true
 tags: [xp, agile, pair-programming, tdd, continuous-integration, collaboration]
 trust_tier: 0
 validation:
-
 ---
 
 # Extreme Programming (XP) Practices
@@ -51,31 +50,6 @@ A: Make test pass + refactor
 
 ## Quick Reference Card
 
-### The Five XP Values
-
-| Value | Meaning | Practice |
-|-------|---------|----------|
-| **Communication** | Everyone knows what everyone does | Daily standups, pairing |
-| **Simplicity** | Simplest thing that works | YAGNI, small design |
-| **Feedback** | Get feedback early and often | TDD, CI, short iterations |
-| **Courage** | Tell truth, adapt | Refactor, admit mistakes |
-| **Respect** | Everyone contributes value | Sustainable pace, pairing |
-
-### Core Practices
-
-| Practice | Description | Benefit |
-|----------|-------------|---------|
-| **Pair Programming** | Two devs, one workstation | Quality + knowledge sharing |
-| **TDD** | Red-Green-Refactor | Confidence + design |
-| **CI** | Integrate multiple times/day | Fast feedback |
-| **Collective Ownership** | Anyone can change anything | No bottlenecks |
-| **Sustainable Pace** | 40-hour weeks | Long-term productivity |
-| **Small Releases** | Ship frequently | Risk reduction |
-
----
-
-## Pair Programming
-
 ### When to Pair
 
 | Context | Pair? | Why |
@@ -87,73 +61,6 @@ A: Make test pass + refactor
 | Simple tasks | ❌ Skip | Not worth overhead |
 | Research spikes | ❌ Skip | Pair to discuss findings |
 
-### Pairing Dos and Don'ts
-
-**Do:**
-- ✅ Switch roles every 20-30 min
-- ✅ Take breaks together
-- ✅ Think out loud
-- ✅ Ask questions
-- ✅ Keep sessions 2-4 hours max
-
-**Don't:**
-- ❌ Grab keyboard without asking
-- ❌ Check phone while pairing
-- ❌ Dominate conversation
-- ❌ Pair all day (exhausting)
-
----
-
-## Ensemble (Mob) Programming
-
-**Setup:** 3+ developers, one screen, rotating driver
-
-```
-[Screen]
-   ↓
-[Driver] ← Directions from navigators
-   ↑
-[Navigator 1] [Navigator 2] [Navigator 3]
-```
-
-**Rotation:** Driver switches every 5-10 min
-
-**Best for:**
-- Complex problem solving
-- Architectural decisions
-- Learning new frameworks
-- Resolving blockers
-
----
-
-## Continuous Integration
-
-**CI Workflow:**
-```
-1. Pull latest from main
-2. Make small change (<2 hrs work)
-3. Run tests locally (all pass)
-4. Commit and push
-5. CI runs tests automatically
-6. If fail → fix immediately
-```
-
-**Best Practices:**
-- Commit frequently (small changes)
-- Keep build fast (<10 min)
-- Fix broken builds immediately
-- Never commit to broken build
-
----
-
-## Four Rules of Simple Design
-
-(In priority order)
-1. **Passes all tests** - Works correctly
-2. **Reveals intention** - Clear, expressive code
-3. **No duplication** - DRY principle
-4. **Fewest elements** - No speculative code
-
 ---
 
 ## Agent Integration
@@ -203,17 +110,6 @@ const xpFleet = await FleetManager.coordinate({
 
 ---
 
-## Common Objections
-
-| Objection | Response |
-|-----------|----------|
-| "Pairing is 2x slower" | 15% slower writing, 15% fewer bugs, net positive |
-| "No time for TDD" | Debugging takes longer than testing |
-| "CI is hard to setup" | Start simple: one action, one test |
-| "Collective ownership = chaos" | Only without tests + CI |
-
----
-
 ## Related Skills
 - [tdd-london-chicago](../tdd-london-chicago/) - TDD deep dive
 - [refactoring-patterns](../refactoring-patterns/) - Safe refactoring
@@ -223,10 +119,6 @@ const xpFleet = await FleetManager.coordinate({
 
 ## Remember
 
-**XP practices work as a system.** Don't cherry-pick randomly:
-- TDD enables collective ownership
-- CI enables small releases
-- Pairing enables collective ownership
-- Sustainable pace enables everything
+**XP practices work as a system** - TDD enables collective ownership, CI enables small releases, pairing enables collective ownership. Don't cherry-pick randomly.
 
-**With Agents:** Agents amplify XP. Pair humans with agents. Agents handle repetitive work, humans provide judgment and creativity.
+**With Agents:** Pair humans with agents. Agents handle repetitive work (regression, data generation, coverage analysis), humans provide judgment and creativity.

package/dist/adapters/claude-flow/detect.d.ts

@@ -34,5 +34,10 @@ export declare function detectClaudeFlow(projectRoot: string): ClaudeFlowDetecti
  * Return a user-friendly message when Claude Flow is not found.
  * Suitable for printing during `aqe init`.
  */
+/**
+ * Resolve the CLI package name: ruflo (preferred) or @claude-flow/cli (fallback).
+ * Used by all bridge modules to build npx args consistently.
+ */
+export declare function resolveCliPackage(): string;
 export declare function getClaudeFlowNotFoundMessage(): string;
 //# sourceMappingURL=detect.d.ts.map

package/dist/adapters/claude-flow/detect.js

@@ -73,7 +73,7 @@ function checkMCPConfig(projectRoot) {
     if (existsSync(mcpJsonPath)) {
         try {
             const config = safeJsonParse(readFileSync(mcpJsonPath, 'utf-8'));
-            if (config.mcpServers?.['claude-flow']) {
+            if (config.mcpServers?.['ruflo'] || config.mcpServers?.['claude-flow']) {
                 return { available: true, method: 'mcp-config' };
             }
         }
@@ -87,7 +87,7 @@ function checkMCPConfig(projectRoot) {
         try {
             const settings = safeJsonParse(readFileSync(settingsPath, 'utf-8'));
             const servers = settings.mcpServers || settings.mcp?.servers || {};
-            if (servers['claude-flow'] || servers['@anthropic/claude-flow']) {
+            if (servers['ruflo'] || servers['claude-flow'] || servers['@anthropic/claude-flow']) {
                 return { available: true, method: 'mcp-config' };
             }
         }
@@ -104,7 +104,7 @@ function checkPackageJson(projectRoot) {
     try {
         const pkg = safeJsonParse(readFileSync(packageJsonPath, 'utf-8'));
         const deps = { ...pkg.dependencies, ...pkg.devDependencies };
-        if (deps['@claude-flow/cli'] || deps['claude-flow']) {
+        if (deps['ruflo'] || deps['@claude-flow/cli'] || deps['claude-flow']) {
             return { available: true, method: 'npm-dependency' };
         }
     }
@@ -114,19 +114,22 @@ function checkPackageJson(projectRoot) {
     return null;
 }
 function checkLocalBinary(projectRoot) {
-    try {
-        // --no-install prevents npx from downloading the package
-        const result = execSync('npx --no-install @claude-flow/cli --version', {
-            encoding: 'utf-8',
-            timeout: 5000,
-            cwd: projectRoot,
-            stdio: ['pipe', 'pipe', 'pipe'], // suppress stderr noise
-        });
-        const version = result.trim().match(/\d+\.\d+\.\d+[\w.-]*/)?.[0];
-        return { available: true, method: 'npx-cached', version };
-    }
-    catch {
-        // Not in npx cache — that's fine, don't try to install it
+    // Try ruflo first, then fall back to @claude-flow/cli
+    for (const pkg of ['ruflo', '@claude-flow/cli']) {
+        try {
+            // --no-install prevents npx from downloading the package
+            const result = execSync(`npx --no-install ${pkg} --version`, {
+                encoding: 'utf-8',
+                timeout: 5000,
+                cwd: projectRoot,
+                stdio: ['pipe', 'pipe', 'pipe'], // suppress stderr noise
+            });
+            const version = result.trim().match(/\d+\.\d+\.\d+[\w.-]*/)?.[0];
+            return { available: true, method: 'npx-cached', version };
+        }
+        catch {
+            // Not in npx cache — that's fine, try next
+        }
     }
     return null;
 }
@@ -137,6 +140,23 @@ function checkLocalBinary(projectRoot) {
  * Return a user-friendly message when Claude Flow is not found.
  * Suitable for printing during `aqe init`.
  */
+/**
+ * Resolve the CLI package name: ruflo (preferred) or @claude-flow/cli (fallback).
+ * Used by all bridge modules to build npx args consistently.
+ */
+export function resolveCliPackage() {
+    for (const pkg of ['ruflo', '@claude-flow/cli']) {
+        try {
+            require.resolve(`${pkg}/package.json`);
+            return pkg;
+        }
+        catch {
+            // not installed, try next
+        }
+    }
+    // Default to ruflo — npx --no-install will fail gracefully if neither is available
+    return 'ruflo';
+}
 export function getClaudeFlowNotFoundMessage() {
     return [
         '  Claude Flow not found — running in standalone mode.',
@@ -147,8 +167,8 @@ export function getClaudeFlowNotFoundMessage() {
         '    - Codebase pretrain analysis',
         '',
         '  To install later:',
-        '    npm install -g @claude-flow/cli',
-        '    claude mcp add claude-flow -- npx -y @claude-flow/cli@latest',
+        '    npm install -g ruflo',
+        '    claude mcp add ruflo -- npx -y ruflo@3.5.18',
         '    aqe init --auto --with-claude-flow',
     ].join('\n');
 }